Centrifugal pump degradation identification based on GA-GMDH algorithm

Objectives In order to monitor the health status of centrifugal pumps in real-time, a model for real-time identification of the degradation state of centrifugal pumps is proposed.

Methods Firstly, based on the operating parameters and degradation mechanism of centrifugal pumps, a combined weighting model using a combination of subjective and objective weights is used to calculate the combined weights, and then a health index during the degradation process of centrifugal pumps is constructed. Secondly, based on existing degradation data of centrifugal pumps, a degradation identification model based on the genetic algorithm - group method of data handling (GA-GMDH) algorithm is proposed.

Results The reliability of the GA-GMDH monitoring model is relatively high, with a root mean square error of 0.029 216 between the output values of the health index and the actual values. The accuracy of degradation state identification based on the model's output results is 93.333%.

Conclusions The research results can provide reference for the health monitoring and maintenance operation management of centrifugal pumps.